Pair2Scene: Learning Local Object Relations for Procedural Scene Generation

• URL: http://arxiv.org/abs/2604.11808v1
• Date: Mon, 13 Apr 2026 17:59:55 GMT
• Title: Pair2Scene: Learning Local Object Relations for Procedural Scene Generation
• Abstract summary: Pair2Scene is a novel procedural generation framework that integrates learned local rules with scene hierarchies and physics-based algorithms.<n>We show that our framework outperforms existing methods in generating complex environments that go beyond training data.
• Score: 10.247549170637418
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating high-fidelity 3D indoor scenes remains a significant challenge due to data scarcity and the complexity of modeling intricate spatial relations. Current methods often struggle to scale beyond training distribution to dense scenes or rely on LLMs/VLMs that lack the ability for precise spatial reasoning. Building on top of the observation that object placement relies mainly on local dependencies instead of information-redundant global distributions, in this paper, we propose Pair2Scene, a novel procedural generation framework that integrates learned local rules with scene hierarchies and physics-based algorithms. These rules mainly capture two types of inter-object relations, namely support relations that follow physical hierarchies, and functional relations that reflect semantic links. We model these rules through a network, which estimates spatial position distributions of dependent objects conditioned on position and geometry of the anchor ones. Accordingly, we curate a dataset 3D-Pairs from existing scene data to train the model. During inference, our framework can generate scenes by recursively applying our model within a hierarchical structure, leveraging collision-aware rejection sampling to align local rules into coherent global layouts. Extensive experiments demonstrate that our framework outperforms existing methods in generating complex environments that go beyond training data while maintaining physical and semantic plausibility.

Related papers

• AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding [55.535374902204296]
  AffordanceVLA is a unified framework that introduces structured affordance forecasting as a task-oriented intermediate representation.<n>We show that AffordanceVLA achieves strong performance across diverse manipulation scenarios.
  arXiv  Detail & Related papers  (2026-06-04T13:28:51Z)
• Interaction Locality in Hierarchical Recursive Reasoning [6.961253535504979]
  spatial reasoning requires both location-bound computation and location-invariant structure.<n>We propose interaction locality, a framework for measuring whether information flow stays within nearby cells or semantic segments, or crosses them.<n>We instantiate the framework with sparse-autoencoder feature ablations and finite-noise activation patching, with structural Jacobian and attention checks reported in the appendix.
  arXiv  Detail & Related papers  (2026-05-20T06:25:49Z)
• SEMASIA: A Large-Scale Dataset of Semantically Structured Latent Representations [12.185380843937196]
  We introduce SEMASIA, a large-scale collection of latent representations extracted from approximately 1,700 pretrained vision models.<n>We analyze the conceptual organization of individual latent spaces, showing consistent prototype-like clustering.<n>We perform a large-scale regression analysis of how pretraining-data complexity, specialization, transfer learning, augmentation, and model scale relate to geometric and probing properties of embeddings.
  arXiv  Detail & Related papers  (2026-05-10T11:42:36Z)
• CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling [18.135856965440784]
  Existing approaches often overlook structural boundaries or rely on fully connected relation graphs that introduce redundant generation errors.<n>Inspired by human design cognition, we present Cas, a cascaded diffusion framework that decomposes the joint scene generation task into four conditional sub-stages.<n>Experiments demonstrate that Cas achieves state-of-the-art performance in fidelity and diversity while enabling improved controllability in practical applications.
  arXiv  Detail & Related papers  (2026-04-30T03:18:26Z)
• Riemannian and Symplectic Geometry for Hierarchical Text-Driven Place Recognition [6.392844932864485]
  SympLoc is a novel coarse-to-fine localization framework with multi-level alignment in the coarse stage.<n>It achieves a 19% improvement in Top-1 recall@10m compared to existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-04-02T04:13:42Z)
• SSR: Pushing the Limit of Spatial Intelligence with Structured Scene Reasoning [30.87517633729756]
  SSR is a framework designed for Structured Scene Reasoning.<n>It seamlessly integrates 2D and 3D representations via a lightweight alignment mechanism.<n>It achieves state-of-the-art performance on multiple spatial intelligence benchmarks.
  arXiv  Detail & Related papers  (2026-02-28T02:05:35Z)
• Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition [63.55828203989405]
  We introduce a novel Topology-Aware Modeling (TAM) framework for Sim2Real UDA on object point clouds.<n>Our approach mitigates the domain gap by leveraging global spatial topology, characterized by low-level, high-frequency 3D structures.<n>We propose an advanced self-training strategy that combines cross-domain contrastive learning with self-training.
  arXiv  Detail & Related papers  (2025-06-26T11:53:59Z)
• HierRelTriple: Guiding Indoor Layout Generation with Hierarchical Relationship Triplet Losses [52.70183252341687]
  We present a hierarchical triplet-based indoor relationship learning method, coined HierRelTriple, with a focus on spatial relationship learning.<n>We introduce HierRelTriple, a hierarchical relational triplets modeling framework that first partitions functional regions and then automatically extracts three levels of spatial relationships.<n>Experiments on unconditional layout synthesis, floorplan-conditioned layout generation, and scene rearrangement demonstrate that HierRel improves spatial-relation metrics by over 15%.
  arXiv  Detail & Related papers  (2025-03-26T07:31:52Z)
• Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion [57.232688209606515]
  We present HTCL, a novel Temporal Temporal Context Learning paradigm for improving camera-based semantic scene completion. Our method ranks $1st$ on the Semantic KITTI benchmark and even surpasses LiDAR-based methods in terms of mIoU.
  arXiv  Detail & Related papers  (2024-07-02T09:11:17Z)
• LAW-Diffusion: Complex Scene Generation by Diffusion with Layouts [107.11267074981905]
  We propose a semantically controllable layout-AWare diffusion model, termed LAW-Diffusion. We show that LAW-Diffusion yields the state-of-the-art generative performance, especially with coherent object relations.
  arXiv  Detail & Related papers  (2023-08-13T08:06:18Z)
• Contrastive Neighborhood Alignment [81.65103777329874]
  We present Contrastive Neighborhood Alignment (CNA), a manifold learning approach to maintain the topology of learned features. The target model aims to mimic the local structure of the source representation space using a contrastive loss. CNA is illustrated in three scenarios: manifold learning, where the model maintains the local topology of the original data in a dimension-reduced space; model distillation, where a small student model is trained to mimic a larger teacher; and legacy model update, where an older model is replaced by a more powerful one.
  arXiv  Detail & Related papers  (2022-01-06T04:58:31Z)
• Multiple Object Tracking with Correlation Learning [16.959379957515974]
  We propose to exploit the local correlation module to model the topological relationship between targets and their surrounding environment. Specifically, we establish dense correspondences of each spatial location and its context, and explicitly constrain the correlation volumes through self-supervised learning. Our approach demonstrates the effectiveness of correlation learning with the superior performance and obtains state-of-the-art MOTA of 76.5% and IDF1 of 73.6% on MOT17.
  arXiv  Detail & Related papers  (2021-04-08T06:48:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.